Image Processing to Detect and ClassifySituations and States of Elderly People

摘要

Monitoring and tracking of elderly people using vision algorithms is anstrategy gaining relevance to detect anomalous and potentially dangerous situa-tions and react immediately. In general vision algorithms for monitoring andtracking are very costly and take a lot of time to respond, which is highly incon-venient since many applications can require action to be taken in real time. Amulti-agent system (MAS) can establish a social model to automate the tasks car-ried out by the human experts during the process of analyzing images obtained bycameras. This study presents a detector agent integrated in a MAS that can proc-ess stereoscopic images to detect and classify situations and states of elderly peo-ple in geriatric residences by combining a series of novel techniques. We will talkin details about the combination of techniques used to perform the detection proc-ess, subdivided into human detection, human tracking ,and human behavior under-standing, and where there is a case-based reasoning (CBR) model that allows thesystem to add reasoning capabilities.